fffiloni's picture
Upload 33 files
fcb4edd verified
import os
import argparse
def parse_args():
parser = argparse.ArgumentParser(description="Simple example of a training script.")
parser.add_argument(
"--pretrained_model_name_or_path",
type=str,
default=None,
required=True,
help="Path to pretrained model or model identifier from huggingface.co/models.",
)
parser.add_argument(
"--variant",
type=str,
default=None,
help="Variant of the model files of the pretrained model identifier from huggingface.co/models, 'e.g.' fp16",
)
parser.add_argument(
"--num_frames",
type=int,
default=25,
help="Number of frames that should be generated in the video.",
)
parser.add_argument(
"--train_data_dir",
type=str,
default=None,
required=True,
help=(
"A folder containing the training data. Folder contents must follow the structure described in"
" https://huggingface.co/docs/datasets/image_dataset#imagefolder. In particular, a `metadata.jsonl` file"
" must exist to provide the captions for the images. Ignored if `dataset_name` is specified."
),
)
parser.add_argument(
"--max_train_samples",
type=int,
default=None,
help=(
"For debugging purposes or quicker training, truncate the number of training examples to this "
"value if set."
),
)
parser.add_argument(
"--double_sampling_rate",
action="store_true",
help=(
"whether or not sampling training frames double rate"
),
)
parser.add_argument(
"--validation_data_dir", type=str, default=None, help="A prompt that is sampled during training for inference."
)
parser.add_argument(
"--num_validation_images",
type=int,
default=4,
help="Number of images that should be generated during validation with `validation_prompt`.",
)
parser.add_argument(
"--validation_epochs",
type=int,
default=1,
help=(
"Run fine-tuning validation every X epochs. The validation process consists of running the prompt"
" `args.validation_prompt` multiple times: `args.num_validation_images`."
),
)
parser.add_argument(
"--output_dir",
type=str,
default="sd-model-finetuned-lora",
help="The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--cache_dir",
type=str,
default=None,
help="The directory where the downloaded models and datasets will be stored.",
)
parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.")
parser.add_argument(
"--train_batch_size", type=int, default=16, help="Batch size (per device) for the training dataloader."
)
parser.add_argument("--num_train_epochs", type=int, default=100)
parser.add_argument(
"--max_train_steps",
type=int,
default=None,
help="Total number of training steps to perform. If provided, overrides num_train_epochs.",
)
parser.add_argument(
"--gradient_accumulation_steps",
type=int,
default=1,
help="Number of updates steps to accumulate before performing a backward/update pass.",
)
parser.add_argument(
"--gradient_checkpointing",
action="store_true",
help="Whether or not to use gradient checkpointing to save memory at the expense of slower backward pass.",
)
parser.add_argument(
"--learning_rate",
type=float,
default=1e-4,
help="Initial learning rate (after the potential warmup period) to use.",
)
parser.add_argument(
"--scale_lr",
action="store_true",
default=False,
help="Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.",
)
parser.add_argument(
"--lr_scheduler",
type=str,
default="constant",
help=(
'The scheduler type to use. Choose between ["linear", "cosine", "cosine_with_restarts", "polynomial",'
' "constant", "constant_with_warmup"]'
),
)
parser.add_argument(
"--lr_warmup_steps", type=int, default=500, help="Number of steps for the warmup in the lr scheduler."
)
parser.add_argument(
"--allow_tf32",
action="store_true",
help=(
"Whether or not to allow TF32 on Ampere GPUs. Can be used to speed up training. For more information, see"
" https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices"
),
)
parser.add_argument(
"--dataloader_num_workers",
type=int,
default=0,
help=(
"Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process."
),
)
parser.add_argument("--adam_beta1", type=float, default=0.9, help="The beta1 parameter for the Adam optimizer.")
parser.add_argument("--adam_beta2", type=float, default=0.999, help="The beta2 parameter for the Adam optimizer.")
parser.add_argument("--adam_weight_decay", type=float, default=1e-2, help="Weight decay to use.")
parser.add_argument("--adam_epsilon", type=float, default=1e-08, help="Epsilon value for the Adam optimizer")
parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.")
parser.add_argument(
"--prediction_type",
type=str,
default=None,
help="The prediction_type that shall be used for training. Choose between 'epsilon' or 'v_prediction' or leave `None`. If left to `None` the default prediction type of the scheduler: `noise_scheduler.config.prediction_type` is chosen.",
)
parser.add_argument(
"--logging_dir",
type=str,
default="logs",
help=(
"[TensorBoard](https://www.tensorflow.org/tensorboard) log directory. Will default to"
" *output_dir/runs/**CURRENT_DATETIME_HOSTNAME***."
),
)
parser.add_argument(
"--mixed_precision",
type=str,
default=None,
choices=["no", "fp16", "bf16"],
help=(
"Whether to use mixed precision. Choose between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >="
" 1.10.and an Nvidia Ampere GPU. Default to the value of accelerate config of the current system or the"
" flag passed with the `accelerate.launch` command. Use this argument to override the accelerate config."
),
)
parser.add_argument(
"--report_to",
type=str,
default="tensorboard",
help=(
'The integration to report the results and logs to. Supported platforms are `"tensorboard"`'
' (default), `"wandb"` and `"comet_ml"`. Use `"all"` to report to all integrations.'
),
)
parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank")
parser.add_argument(
"--checkpointing_steps",
type=int,
default=500,
help=(
"Save a checkpoint of the training state every X updates. These checkpoints are only suitable for resuming"
" training using `--resume_from_checkpoint`."
),
)
parser.add_argument(
"--checkpoints_total_limit",
type=int,
default=None,
help=("Max number of checkpoints to store."),
)
parser.add_argument(
"--resume_from_checkpoint",
type=str,
default=None,
help=(
"Whether training should be resumed from a previous checkpoint. Use a path saved by"
' `--checkpointing_steps`, or `"latest"` to automatically select the last available checkpoint.'
),
)
parser.add_argument(
"--enable_xformers_memory_efficient_attention", action="store_true", help="Whether or not to use xformers."
)
parser.add_argument("--noise_offset", type=float, default=0, help="The scale of noise offset.")
parser.add_argument(
"--rank",
type=int,
default=4,
help=("The dimension of the LoRA update matrices."),
)
args = parser.parse_args()
env_local_rank = int(os.environ.get("LOCAL_RANK", -1))
if env_local_rank != -1 and env_local_rank != args.local_rank:
args.local_rank = env_local_rank
return args